Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Arc

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ithand
    -0.08
    amisesta
    -0.08
     Restore
    -0.07
    OCs
    -0.07
    ��
    -0.07
     mediation
    -0.07
    ធី
    -0.07
    ovým
    -0.07
     librarians
    -0.07
    SOC
    -0.07
    POSITIVE LOGITS
     fizik
    0.08
     calorie
    0.08
     decoder
    0.08
    (recipe
    0.08
    ülle
    0.08
     nowhere
    0.08
    ěr
    0.08
    Anzeige
    0.07
     física
    0.07
     Aussage
    0.07
    Act Density 0.001%

    No Known Activations